AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens

Zekun Li, Sizhe An, Chengcheng Tang, Chuan Guo, Ivan Shugurov, Linguang Zhang, Amy Zhao, Srinath Sridhar, Lingling Tao, Abhay Mittal

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Text-driven human motion generation · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use modality-specific MoT with frozen text modules instead of full LLM fine-tuning (3B) (ablation)LLaMo · MMLUaccuracy: 24.9 -> 63.4Improved
use MoT with frozen text modules instead of full fine-tuning (1B) (ablation)LLaMo · MMLUaccuracy: 26.6 -> 49.3Improved
use MoT instead of full fine-tuning (3B) (ablation)LLaMo · Own large-scale motion-text test split (~30K)FID: 46.174 -> 19.893Improved
use MoT instead of full fine-tuning (1B) (ablation)LLaMo · Own large-scale motion-text test split (~30K)FID: 63.215 -> 27.361Improved
use MoT instead of full fine-tuning (3B) (ablation)LLaMo · Own large-scale motion-text test split (~30K)text-to-motion R@3: 0.8307 -> 0.9594Improved
use MoT instead of full fine-tuning (3B) (ablation)LLaMo · Own large-scale motion-text test split (~30K)motion-to-text R@3: 0.9412 -> 0.9422No clear effect
scale LLaMo from 1B to 3B (ablation)LLaMo · HumanML3D text-to-motionFID: 53.942 -> 22.491Improved
scale LLaMo from 1B to 3B (ablation)LLaMo · HumanML3D motion-to-textCIDEr: 104.7 -> 100.8No clear effect
use continuous causal VAE instead of FSQ discrete tokenizer (ablation)motion codec · Motion reconstructionMPJPE: 41.9 -> 10.1Improved
increase VAE latent dimension from 32 to 64 (ablation)causal VAE · Motion reconstructionMPJPE: 10.1 -> 3.86Improved
LLaMo vs specialist models on HumanML3D FIDLLaMo-3B vs MotionStreamer · HumanML3D text-to-motionFID: 11.790 -> 22.491Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy